Cluster retrieval assumes that the probability of relevance of a document should depend on the relevance of other similar documents to the same query. The goal is to find the best group of documents. Many studies have examined the effectiveness of this approach, by employing different retrieval methods or clustering algorithms, but few have investigated text representations. This paper revisits...

Abstract While travel cost in urban areas is generally best modeled using network distances, continuous distance measures are mostly used for location problems in rural environments. Combining both is not only interesting from a modeling perspective, but has also computational advantages since it combines reduced storage requirements for the network data with a high accuracy of the approximated...

This paper presents a first investigation on the structure from motion problem from the combination of full and weak perspective images. This problem arises in multiresolution object modeling, where multiple zoomed-in or closeup views are combined with wider or distant reference views. The narrow field-of-view (FOV) images from the zoomed-in or closeup views can be approximated as weak perspect...

Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving its powerful spatial representation ability. It challenging to estimate the BEV maps from monocular images due gap, since it implicitly required realize both perspective-to-BEV transformation and segmentation. We present a novel two-stage Geometry PrIor-based Transformation framework named GitNet, consisting of (i) ge...

With a number of students, the purpose of collaborative learning is to assign these students to the right teams so that the promotion of skills of each team member can be facilitated. Although some team formation solutions have been proposed, the problem of extracting more effective features to describe the skill proficiency of students for better collaborative learning is still open. To that e...

Models provide an alternative perspective for the understanding of a software system. However, models reflect the state of the system at the time of their creation (or last updating) but they do not reflect intermediate changes during the system’s evolution. Depicting perspectives without showing changes is like watching a movie through a small set of still pictures (i.e., no motion). This pape...

Teaching software engineering in an applied setting with projects provided by clients from industry creates a realworld learning experience for students. While clients are domain experts well-aware of the system’s requirements, they often lack technical knowledge required to make decisions regarding the system architecture or the technologies involved in the project. Therefore, it is challengin...

In this paper the architecture and implementation of Cooperative Information Agents (CIA) is described. Taking a language-action perspective to the design of CIAs allows for the specification of obligations and authorizations, and results in the separation of tasks (things the agent must do) and contracts (mutually agreed commitments to the course of communication). The architecture describes t...

We shed new light on the long-debated question about the nature of mental images, that is, the underlying structures and processes, with a new theory of mental imagery. This theory is formalized as a computational cognitive model and provides an integrated account of the three prevalent theories of mental imagery, i.e., the descriptive, the quasi-pictorial, and the enactive theory. It does so b...